報(bào)告題目：Multi-task Deep Learning for Human Action Parsing
報(bào)告人：邵嶺(Ling Shao) 博士, Chair Professor, Fellow of IET
單位：Northumbria University
報(bào)告時(shí)間：2016年9月1日(周四)下午14:30-16:00
報(bào)告地點(diǎn)：屯溪路校區(qū)逸夫樓408會(huì)議室
報(bào)告摘要：Automatically recognizing objects, scenes and actions is a core component of an artificial intelligence system. In this talk, I will cover two of my main research areas – human action recognition and deep learning. Action recognition has been an active research topic in computer vision due to its various applications in human-machine interaction, robotics, video surveillance and visual big data search. I will first review some related work on handcrafted features, feature/deep learning and attributes learning. Then I will introduce our recent multi-task system that can jointly solve three main problems: 1) Where in the video do the actions occur? (2) What categories do the actions belong to? and (3) How are these actions performed? This multi-task learning framework is designed based on a state-of-the-art 3D deep convolutional neural network (3D-CNN). Specifically, in the training phase, action localization, classification and attributes learning can be jointly optimized via the proposed deep architecture. Once model training is completed, given an upcoming test video, we can describe each individual action in the video simultaneously as: where the action occurs, what the action is and how the action is performed. To train the deep network, we also introduce a new large-scale aligned action dataset, NASA, with 200K well labeled video clips. Finally, I will present the results of detailed action parsing on challenging, realistic datasets that are collected by us or publicly available. Some initial results on zero-shot learning via the obtained action attributes will be discussed too.
報(bào)告人簡(jiǎn)介：邵嶺教授于中國(guó)科學(xué)技術(shù)大學(xué)獲得學(xué)士學(xué)位，在英國(guó)牛津大學(xué)獲得碩士和博士學(xué)位。邵嶺教授在學(xué)術(shù)界和工業(yè)界有著豐富的工作經(jīng)驗(yàn)，現(xiàn)任英國(guó)Northumbria University 計(jì)算機(jī)與信息科學(xué)系首席教授，并將于2016年11月份加盟University of East Anglia任計(jì)算機(jī)系首席教授。邵嶺教授在計(jì)算機(jī)視覺(jué)、圖像/視頻處理、模式識(shí)別與機(jī)器學(xué)習(xí)領(lǐng)域取得了豐碩的研究成果，在PAMI、TIP、TNNLS、IJCV等頂尖國(guó)際期刊和CVPR、ICCV、ECCV、MM、IJCAI等頂尖國(guó)際會(huì)議發(fā)表論文超過(guò)200篇，并擁有超過(guò)10項(xiàng)美國(guó)/歐盟專(zhuān)利。邵嶺教授目前擔(dān)任TNNLS、TIP、TCSVT、ToC等頂尖期刊的副主編，同時(shí)也是ICPR、BMVC、ICME等著名國(guó)際會(huì)議領(lǐng)域主席，ICCV、CVPR、ECCV、MM等頂尖會(huì)議程序委員會(huì)委員。邵嶺教授是IET學(xué)會(huì)會(huì)士、英國(guó)計(jì)算機(jī)學(xué)會(huì)會(huì)士、IEEE高級(jí)會(huì)員、ACM終身會(huì)員。
太陽(yáng)集團(tuán)tyc5997
TOP
